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. 65835
    Prev
    Next
    INDEX
    Explanations

    a

    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
     vice
    -0.08
     بر
    -0.08
    ーム
    -0.08
    inje
    -0.07
     مم
    -0.07
    وبي
    -0.07
     छोट
    -0.07
     lingering
    -0.07
     mosaic
    -0.07
     Leuven
    -0.07
    POSITIVE LOGITS
    _is
    0.09
     ilişk
    0.09
     Hosts
    0.08
     relasyon
    0.08
    .is
    0.08
     отношения
    0.08
    _relation
    0.08
     राश
    0.08
     langwe
    0.08
    _it
    0.08
    Activations Density 0.028%

    No Known Activations