© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 50264
    Prev
    Next
    INDEX
    Explanations

    细

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intérêt
    -0.09
     realities
    -0.09
     interest
    -0.08
    _interest
    -0.08
     الصحيح
    -0.08
    -interest
    -0.08
     Realität
    -0.08
     साव
    -0.07
     interés
    -0.07
     orderly
    -0.07
    POSITIVE LOGITS
    粒
    0.20
    致
    0.16
    化
    0.15
    颗
    0.15
    -gr
    0.14
    分
    0.13
     gran
    0.12
     granular
    0.12
     gr
    0.12
    grain
    0.12
    Activations Density 0.003%

    No Known Activations