Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54167
    Prev
    Next
    INDEX
    Explanations

    mentioned

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ITS
    -0.08
     privilégi
    -0.08
    _assert
    -0.07
    #pragma
    -0.07
    credit
    -0.07
    mtp
    -0.07
     unsolicited
    -0.07
    arten
    -0.07
     BCM
    -0.07
     bcm
    -0.06
    POSITIVE LOGITS
     คือ
    0.09
     dedans
    0.08
     хуже
    0.08
     haber
    0.08
     homer
    0.08
     Hoch
    0.08
     ได้แก่
    0.08
    仕様
    0.08
     पद
    0.08
     terribly
    0.08
    Activations Density 0.002%

    No Known Activations