© 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. 23-RESID-POST-AA
    11. 97449
    Prev
    Next
    INDEX
    Explanations

    Roman bureaucracy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    member
    -0.09
    dias
    -0.08
    jie
    -0.08
    committee
    -0.08
     ceramic
    -0.08
     дзі
    -0.08
    assessment
    -0.08
    /member
    -0.07
     Département
    -0.07
     fleur
    -0.07
    POSITIVE LOGITS
    (sm
    0.11
     sm
    0.10
    _sm
    0.10
    	sm
    0.09
     см
    0.08
    .sm
    0.08
    sm
    0.08
    -sm
    0.08
    喝
    0.08
    翁
    0.08
    Activations Density 0.000%

    No Known Activations