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. 53879
    Prev
    Next
    INDEX
    Explanations

    comprehensive

    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
     మీద
    -0.09
     perju
    -0.08
     reclaimed
    -0.08
     Offset
    -0.08
     Gall
    -0.08
     चाहे
    -0.08
    _ASSIGN
    -0.08
     делу
    -0.08
     Dha
    -0.08
     jealous
    -0.07
    POSITIVE LOGITS
     schematic
    0.08
     questionnaire
    0.08
     sche
    0.07
     explanatory
    0.07
     ast
    0.07
     koek
    0.07
    chematic
    0.07
     synthesis
    0.07
     použ
    0.07
    badge
    0.07
    Activations Density 0.001%

    No Known Activations