© 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. 79010
    Prev
    Next
    INDEX
    Explanations

    negative outcomes

    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
     e
    -0.08
    -0.08
     (
    -0.08
     concerns
    -0.07
     with
    -0.07
    :↵↵
    -0.07
     A
    -0.07
    :
    -0.07
     "
    -0.07
     in
    -0.07
    POSITIVE LOGITS
    无法
    0.12
     irrev
    0.12
     unstoppable
    0.12
     hopeless
    0.12
     unavoidable
    0.11
     dauerhaft
    0.11
     inevit
    0.11
     prognosis
    0.11
     невозмож
    0.11
     irreversible
    0.11
    Activations Density 0.137%

    No Known Activations