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. 112968
    Prev
    Next
    INDEX
    Explanations

    salty

    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
     Porta
    -0.09
     RTP
    -0.08
    (zone
    -0.08
     Angelo
    -0.08
     MTB
    -0.07
     mot
    -0.07
     Banana
    -0.07
    isu
    -0.07
    itrine
    -0.07
     Purple
    -0.07
    POSITIVE LOGITS
     soldier
    0.07
    ;</
    0.07
    智能
    0.07
    램
    0.07
     slechts
    0.07
    sement
    0.07
    "</
    0.07
     físicas
    0.07
    oram
    0.07
     bary
    0.07
    Activations Density 0.053%

    No Known Activations