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

    Neuronpedia

    APICircuit 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. 15-RESID-POST-AA
    6. 92
    Prev
    Next
    INDEX
    Explanations

    leaving a border

    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
    keyboard
    -0.09
     verkeerd
    -0.08
     keyboard
    -0.08
    _wrong
    -0.08
    keyword
    -0.08
    _force
    -0.08
    _switch
    -0.07
    强
    -0.07
    Wrong
    -0.07
    (identifier
    -0.07
    POSITIVE LOGITS
    Insets
    0.09
     ಸುಮಾರು
    0.09
     حدود
    0.08
     Wembley
    0.08
     چو
    0.08
     līdz
    0.08
     satria
    0.08
     margen
    0.08
    .sa
    0.08
     piedi
    0.08
    Activations Density 0.001%

    No Known Activations