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. 11-RESID-POST-AA
    6. 53248
    Prev
    Next
    INDEX
    Explanations

    _open

    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
     vibes
    -0.08
    égation
    -0.08
     BDSM
    -0.08
     δω
    -0.08
     budding
    -0.08
    antai
    -0.07
    Sexy
    -0.07
     networking
    -0.07
     stitches
    -0.07
     strains
    -0.07
    POSITIVE LOGITS
    .backward
    0.08
     сделать
    0.07
     terminar
    0.07
     хороший
    0.07
     tm
    0.07
    inad
    0.07
     кое
    0.07
     Challenger
    0.07
    (ar
    0.07
     Disconnect
    0.07
    Activations Density 0.001%

    No Known Activations