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. 43145
    Prev
    Next
    INDEX
    Explanations

    problems and challenges

    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
     evolución
    -0.09
    डा
    -0.08
     gär
    -0.08
     ryth
    -0.08
     scrolling
    -0.08
    ılık
    -0.07
    ires
    -0.07
     Engelse
    -0.07
     disposizione
    -0.07
    beln
    -0.07
    POSITIVE LOGITS
     mainstream
    0.11
     prohibits
    0.11
     forb
    0.11
     forbid
    0.10
     refuses
    0.10
     permits
    0.10
    拒
    0.09
     hesitant
    0.09
     refused
    0.09
     refusal
    0.08
    Activations Density 0.152%

    No Known Activations