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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19466
    Prev
    Next
    INDEX
    Explanations

    Web snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    кового
    -0.08
    ковой
    -0.08
     matured
    -0.07
    жат
    -0.07
    way
    -0.07
    ways
    -0.07
    @endsection
    -0.07
     måte
    -0.07
     manière
    -0.07
     અનેક
    -0.07
    POSITIVE LOGITS
    XD
    0.09
    .d
    0.08
    Foundation
    0.08
     kısa
    0.08
     sèche
    0.08
    0.08
     {
    
    ↵
    0.08
    .scale
    0.08
    ದಿ
    0.08
    .short
    0.07
    Activations Density 0.056%

    No Known Activations