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. 54079
    Prev
    Next
    INDEX
    Explanations

    shapes and areas

    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
    նի
    -0.08
    нив
    -0.08
    ဏ
    -0.08
    ែន
    -0.07
    រ
    -0.07
    ែក
    -0.07
     tailor
    -0.07
     Chief
    -0.07
     tanben
    -0.07
    ​ក
    -0.07
    POSITIVE LOGITS
    sq
    0.09
    ANGE
    0.08
    RARY
    0.08
    Odds
    0.08
    Termination
    0.08
    Frank
    0.08
     nestled
    0.08
    Docker
    0.08
    Woo
    0.07
    CIPE
    0.07
    Activations Density 0.030%

    No Known Activations