© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68309
    Prev
    Next
    INDEX
    Explanations

    math operations

    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
     storm
    -0.08
     fisk
    -0.08
     vang
    -0.08
     lg
    -0.07
    uleiro
    -0.07
     Storm
    -0.07
     cocok
    -0.07
     Kristen
    -0.07
     Guangzhou
    -0.07
     lesbians
    -0.07
    POSITIVE LOGITS
     ::=
    0.09
     refinement
    0.09
     jederzeit
    0.09
     refine
    0.09
     selectable
    0.09
     sublic
    0.08
    Unary
    0.08
     (§
    0.08
     combinations
    0.08
     manipulation
    0.08
    Activations Density 0.014%

    No Known Activations