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. 54241
    Prev
    Next
    INDEX
    Explanations

    Counting

    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
    особ
    -0.09
    �
    -0.08
    ोजन
    -0.08
    .Util
    -0.08
     mainstream
    -0.07
    maßnahmen
    -0.07
    _management
    -0.07
    ?|
    -0.07
    .Linq
    -0.07
    .Drawable
    -0.07
    POSITIVE LOGITS
     вверх
    0.11
     ascend
    0.10
     crescendo
    0.09
     aloud
    0.09
     Audible
    0.08
    ಕ್ರಮ
    0.08
    轨
    0.08
     habl
    0.08
     numbering
    0.08
     incre
    0.08
    Activations Density 0.015%

    No Known Activations