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. 7-RESID-POST-AA
    6. 131043
    Prev
    Next
    INDEX
    Explanations

    ye

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rails
    -0.08
    Connectivity
    -0.08
     shores
    -0.08
     connectivity
    -0.08
     остров
    -0.08
     П
    -0.08
    Kenn
    -0.07
     arsen
    -0.07
     Connectivity
    -0.07
    quila
    -0.07
    POSITIVE LOGITS
     overwrite
    0.08
     overe
    0.08
     perspect
    0.07
     Mali
    0.07
     ipsum
    0.07
    0.07
     projections
    0.07
     parag
    0.07
     enthous
    0.07
     astronomy
    0.07
    Activations Density 0.020%

    No Known Activations