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. 11832
    Prev
    Next
    INDEX
    Explanations

    slide

    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
     simb
    -0.09
     Pflege
    -0.08
    ertid
    -0.08
     എണ്ണ
    -0.08
    erdas
    -0.08
    poses
    -0.08
    tips
    -0.08
    _calls
    -0.07
    _notes
    -0.07
    개의
    -0.07
    POSITIVE LOGITS
    .horizontal
    0.10
     horizontal
    0.10
     horizontally
    0.10
    -horizontal
    0.09
    0.09
    horizontal
    0.08
    -r
    0.08
    -right
    0.08
     Horizontal
    0.08
     effect
    0.08
    Activations Density 0.003%

    No Known Activations