© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18894
    Prev
    Next
    INDEX
    Explanations

    might/maybe

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     provavelmente
    -0.13
     likely
    -0.13
     vermutlich
    -0.13
     waarschijnlijk
    -0.13
     presumably
    -0.12
     wahrscheinlich
    -0.12
     probablemente
    -0.12
     presumed
    -0.11
     probably
    -0.11
     Probably
    -0.10
    POSITIVE LOGITS
     parfois
    0.16
     joskus
    0.15
     Sometimes
    0.15
     certains
    0.15
     sometimes
    0.15
    Sometimes
    0.15
     bazı
    0.14
    บาง
    0.14
     manchmal
    0.14
    sometimes
    0.14
    Activations Density 0.049%

    No Known Activations