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. 60723
    Prev
    Next
    INDEX
    Explanations

    Rhymes and poems

    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
     Interpretation
    -0.07
     interpretation
    -0.07
     Broadcasting
    -0.07
     preprocess
    -0.07
    .Users
    -0.07
     Moment
    -0.07
     prévenir
    -0.07
     Negoti
    -0.07
    .ndarray
    -0.07
    184
    -0.07
    POSITIVE LOGITS
    Pairs
    0.10
    pairs
    0.10
    Pair
    0.10
    _pairs
    0.09
     الرب
    0.09
     pairs
    0.09
    _pair
    0.09
    끝
    0.08
     тап
    0.08
     аяқ
    0.08
    Activations Density 0.010%

    No Known Activations