© 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. 3-RESID-POST-AA
    11. 2725
    Prev
    Next
    INDEX
    Explanations

    large

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odzi
    -0.09
     pochi
    -0.09
     licz
    -0.08
     Till
    -0.08
     Leap
    -0.08
     preciso
    -0.07
     torr
    -0.07
     légèrement
    -0.07
     кожи
    -0.07
     Claro
    -0.07
    POSITIVE LOGITS
     conglomer
    0.09
    HSV
    0.08
    wt
    0.08
     UNESCO
    0.07
     desal
    0.07
     unconscious
    0.07
     SNP
    0.07
    upr
    0.07
     Migr
    0.07
    yellow
    0.07
    Activations Density 0.016%

    No Known Activations