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. 11710
    Prev
    Next
    INDEX
    Explanations

    ative

    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
    61
    -0.09
    .log
    -0.08
    273
    -0.08
    ══
    -0.07
    .exp
    -0.07
    _cpu
    -0.07
    /aut
    -0.07
     Ann
    -0.07
    391
    -0.07
    Comput
    -0.07
    POSITIVE LOGITS
     Femin
    0.08
     Masa
    0.08
     Eisen
    0.08
     mutil
    0.08
    лиф
    0.08
     необ
    0.08
     наполн
    0.08
     bajo
    0.08
     androgen
    0.08
     Driven
    0.08
    Activations Density 0.001%

    No Known Activations