© 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. 11-RESID-POST-AA
    11. 47255
    Prev
    Next
    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     underside
    -0.08
    -det
    -0.08
    Viewed
    -0.07
    yards
    -0.07
     пит
    -0.07
     된
    -0.07
    abolic
    -0.07
     Trout
    -0.07
     Voir
    -0.07
     রেখ
    -0.07
    POSITIVE LOGITS
    hm
    0.09
    147
    0.08
    MAX
    0.08
    ân
    0.07
    ın
    0.07
    ":"","
    0.07
    �
    0.07
    crm
    0.07
     *,↵
    0.07
     Doug
    0.07
    Activations Density 0.008%

    No Known Activations