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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 1818
    Prev
    Next
    INDEX
    Explanations

    preliminary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     repr
    -0.07
     Leib
    -0.07
     Occ
    -0.07
    каж
    -0.07
     literal
    -0.07
     generations
    -0.07
    �
    -0.07
     комбина
    -0.07
    nbsp
    -0.07
     yerine
    -0.07
    POSITIVE LOGITS
     prelim
    0.09
     preliminary
    0.09
     hostile
    0.08
    ilan
    0.08
     ipp
    0.08
    तः
    0.08
     rud
    0.08
    liminary
    0.08
    荣
    0.08
     boc
    0.08
    Activations Density 0.006%

    No Known Activations