© 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. 26469
    Prev
    Next
    INDEX
    Explanations

    cryptocurrency

    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
     vakar
    -0.08
    -kan
    -0.08
     Dresses
    -0.08
     آواز
    -0.08
     kveld
    -0.08
    wirk
    -0.08
     flam
    -0.08
    -lang
    -0.08
     Hart
    -0.08
     chewing
    -0.08
    POSITIVE LOGITS
    Nonce
    0.09
    _nonce
    0.08
    nonce
    0.08
     feasibility
    0.08
     feasible
    0.08
    Outcome
    0.08
    Objective
    0.07
    goal
    0.07
     nonce
    0.07
    objective
    0.07
    Activations Density 0.001%

    No Known Activations