© 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. 48474
    Prev
    Next
    INDEX
    Explanations

    equals sign

    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
     habari
    -0.09
    pea
    -0.09
    mw
    -0.08
     informacion
    -0.08
     bwe
    -0.08
    dde
    -0.08
    gema
    -0.08
    blad
    -0.08
     respectfully
    -0.08
    /widget
    -0.08
    POSITIVE LOGITS
     seuls
    0.08
     quem
    0.08
    Someone
    0.08
    _WH
    0.07
    란
    0.07
    Basics
    0.07
    ਸ਼
    0.07
    ੂ
    0.07
     Alone
    0.07
    ূ
    0.07
    Activations Density 0.007%

    No Known Activations