© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 26374
    Prev
    Next
    INDEX
    Explanations

    37

    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
    Mocks
    -0.09
     consac
    -0.08
     crispy
    -0.08
    -original
    -0.08
    _ATTR
    -0.07
    енности
    -0.07
     αγα
    -0.07
    ригин
    -0.07
    рон
    -0.07
    original
    -0.07
    POSITIVE LOGITS
     fuori
    0.09
     derrière
    0.08
     fueled
    0.08
    uš
    0.08
     occult
    0.08
     Jahre
    0.08
     fuels
    0.08
     apparten
    0.08
     Farrell
    0.08
    uttur
    0.08
    Activations Density 0.001%

    No Known Activations