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. 43602
    Prev
    Next
    INDEX
    Explanations

    period

    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
    ,而且
    -0.08
    yb
    -0.07
    vae
    -0.07
    hr
    -0.07
     Diaries
    -0.07
     MES
    -0.07
    MIN
    -0.07
    32
    -0.07
     وأن
    -0.07
    Fake
    -0.07
    POSITIVE LOGITS
    uty
    0.09
     namely
    0.08
     보면
    0.08
    л
    0.08
    например
    0.08
     trabalh
    0.07
     됩니다
    0.07
    дв
    0.07
    ക്ത
    0.07
    ูล
    0.07
    Activations Density 0.061%

    No Known Activations