© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29780
    Prev
    Next
    INDEX
    Explanations

    general/typical information

    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
     최초
    -0.09
     brethren
    -0.09
    ≤
    -0.08
     grotes
    -0.08
     aparentemente
    -0.08
     ???↵↵
    -0.08
     меня
    -0.08
     gimm
    -0.08
     tão
    -0.08
    Kill
    -0.08
    POSITIVE LOGITS
     costuma
    0.08
    0.08
    :")↵
    0.08
    .criteria
    0.08
     faz
    0.07
     oatmeal
    0.07
     explore
    0.07
    :\
    0.07
     ERP
    0.07
     customizable
    0.07
    Activations Density 0.130%

    No Known Activations