© 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. 48714
    Prev
    Next
    INDEX
    Explanations

    autom

    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
     disease
    -0.08
     ezigbo
    -0.08
    ýär
    -0.08
     koristiti
    -0.08
    auri
    -0.08
     Daughter
    -0.08
     doma
    -0.08
     Capitals
    -0.08
     zile
    -0.08
     Overlay
    -0.08
    POSITIVE LOGITS
    ROLL
    0.08
    pä
    0.08
    rol
    0.07
    EC
    0.07
     adjusted
    0.07
    rolling
    0.07
     recognition
    0.07
    encode
    0.07
     கவ
    0.07
     ટી
    0.07
    Activations Density 0.000%

    No Known Activations