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. 58506
    Prev
    Next
    INDEX
    Explanations

    ically

    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
    Gar
    -0.08
     आए
    -0.08
    zim
    -0.08
    ented
    -0.07
    ENN
    -0.07
     desperately
    -0.07
     cherish
    -0.07
    Hay
    -0.07
    iffel
    -0.07
    Estim
    -0.07
    POSITIVE LOGITS
     technically
    0.11
     theoretically
    0.11
     feas
    0.09
     técn
    0.08
     говоря
    0.08
    来说
    0.08
     conce
    0.08
     standpoint
    0.08
    techn
    0.07
     तौर
    0.07
    Activations Density 0.020%

    No Known Activations