© 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. 18344
    Prev
    Next
    INDEX
    Explanations

    advantages

    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
     Anzahl
    -0.07
     expected
    -0.07
    (?)
    -0.07
    Sehr
    -0.07
     stb
    -0.07
     centaines
    -0.07
     (?)
    -0.07
     paar
    -0.06
    Expected
    -0.06
     notified
    -0.06
    POSITIVE LOGITS
    作为
    0.14
     helps
    0.13
     ככל
    0.13
     Helps
    0.12
     avulla
    0.12
     помогает
    0.12
     alone
    0.12
     mangrupikeun
    0.11
     contributes
    0.11
     способствует
    0.11
    Activations Density 0.417%

    No Known Activations