© 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. 96773
    Prev
    Next
    INDEX
    Explanations

    Math and foreign languages

    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
     pax
    -0.07
    zell
    -0.07
    istical
    -0.07
     pust
    -0.07
    atação
    -0.07
     abo
    -0.07
    してください
    -0.07
    యం
    -0.07
    anta
    -0.07
     сход
    -0.07
    POSITIVE LOGITS
     displays
    0.08
    Plant
    0.08
    arc
    0.08
    'esp
    0.07
     manif
    0.07
     સમ
    0.07
    volver
    0.07
     artes
    0.07
    Bi
    0.07
     flask
    0.07
    Activations Density 0.025%

    No Known Activations