Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43442
    Prev
    Next
    INDEX
    Explanations

    deliver

    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
    (:,
    -0.08
     percentile
    -0.07
     نقاط
    -0.07
     @(
    -0.07
     member
    -0.07
    @(
    -0.07
     points
    -0.07
    Member
    -0.07
    points
    -0.07
     ratings
    -0.06
    POSITIVE LOGITS
     espont
    0.10
     самостоятельно
    0.09
     unkompl
    0.09
     spontan
    0.09
     kinak
    0.09
     diagnosing
    0.08
     Versorgung
    0.08
     peacefully
    0.08
     denúncia
    0.08
    jing
    0.08
    Activations Density 0.009%

    No Known Activations