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. 49790
    Prev
    Next
    INDEX
    Explanations

    +

    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
    temper
    -0.08
    -ию
    -0.08
     ohjel
    -0.08
    (download
    -0.08
    _archive
    -0.08
     rivalry
    -0.08
    aktiv
    -0.08
     Jakob
    -0.08
     akty
    -0.08
    _lazy
    -0.08
    POSITIVE LOGITS
    ù
    0.09
     Weighted
    0.09
    ్బ
    0.08
     Projection
    0.08
     weighted
    0.08
     instrumental
    0.08
     projection
    0.08
     linear
    0.08
     Instrument
    0.08
     दिशा
    0.08
    Activations Density 0.061%

    No Known Activations