© 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. 96897
    Prev
    Next
    INDEX
    Explanations

    sport games

    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
    metrical
    -0.08
     аб
    -0.08
    дегі
    -0.08
    abte
    -0.08
     adrenaline
    -0.08
     Selle
    -0.07
    garh
    -0.07
    enemy
    -0.07
     Türkmen
    -0.07
    _sep
    -0.07
    POSITIVE LOGITS
     kir
    0.08
     Embed
    0.07
    ices
    0.07
     Chesapeake
    0.07
     Cl
    0.07
     Dollar
    0.07
     atoms
    0.07
     basiss
    0.07
    .Name
    0.07
     Accounting
    0.07
    Activations Density 0.000%

    No Known Activations