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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 106336
    Prev
    Next
    INDEX
    Explanations

    jnana yoga

    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
    _vi
    -0.08
    os
    -0.08
    rices
    -0.08
     sentiments
    -0.08
     satellites
    -0.07
     ACS
    -0.07
     Satell
    -0.07
     principaux
    -0.07
     AS
    -0.07
    iak
    -0.07
    POSITIVE LOGITS
     Sonny
    0.08
     holders
    0.08
    Converters
    0.08
    (det
    0.07
     mattered
    0.07
     #(
    0.07
     ソ
    0.07
    cancel
    0.07
    소드
    0.07
    Canc
    0.07
    Activations Density 0.001%

    No Known Activations