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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 95299
    Prev
    Next
    INDEX
    Explanations

    dot product equations

    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
     widening
    -0.08
    மை
    -0.07
     pronounce
    -0.07
     வ
    -0.07
    भर
    -0.07
    western
    -0.07
     ак
    -0.07
    ul
    -0.07
     vast
    -0.07
     കൊണ്ട
    -0.07
    POSITIVE LOGITS
     অপর
    0.08
     polic
    0.08
     Myst
    0.08
    insics
    0.08
     себя
    0.07
     geom
    0.07
     examines
    0.07
     nj
    0.07
     cherchez
    0.07
     вообще
    0.07
    Activations Density 0.010%

    No Known Activations