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. 52973
    Prev
    Next
    INDEX
    Explanations

    time duration

    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
     પ્રમ
    -0.09
     ప్రమ
    -0.08
     മാർ
    -0.08
    ик
    -0.08
     antigen
    -0.08
     predomin
    -0.08
     criteria
    -0.08
    نمای
    -0.07
    /apps
    -0.07
     fonte
    -0.07
    POSITIVE LOGITS
    	buffer
    0.10
     Reservoir
    0.09
     buff
    0.09
     foam
    0.09
     Foam
    0.08
     Buffer
    0.08
     buf
    0.08
    .buffer
    0.08
    	buf
    0.08
     beträgt
    0.08
    Activations Density 0.003%

    No Known Activations