© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 78411
    Prev
    Next
    INDEX
    Explanations

    eighth

    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
     confront
    -0.08
     позволя
    -0.07
    allowed
    -0.07
     clever
    -0.07
     tam
    -0.07
     permet
    -0.07
     strategies
    -0.07
    ifest
    -0.07
     ingen
    -0.07
    _algo
    -0.07
    POSITIVE LOGITS
     ș
    0.08
    ulose
    0.08
     شر
    0.08
    -packed
    0.08
     Jesu
    0.08
     Ordin
    0.08
     tekk
    0.08
    atae
    0.07
    級
    0.07
     الشر
    0.07
    Activations Density 0.001%

    No Known Activations