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. 102892
    Prev
    Next
    INDEX
    Explanations

    linux

    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
    Recognizer
    -0.07
    Ө
    -0.07
    Ā
    -0.07
    ces
    -0.07
    ─
    -0.07
     meld
    -0.07
    Aer
    -0.07
    uasive
    -0.07
     operation
    -0.07
    写真
    -0.07
    POSITIVE LOGITS
    _pickle
    0.08
     cylind
    0.08
    .Dimension
    0.08
     Ngb
    0.08
     lưu
    0.08
     luk
    0.08
     Pkw
    0.08
    .dimension
    0.07
    ());//
    0.07
     combustible
    0.07
    Activations Density 0.002%

    No Known Activations