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. 52788
    Prev
    Next
    INDEX
    Explanations

    Pulse

    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
     Ouro
    -0.09
     Wheel
    -0.08
     Orch
    -0.08
     unquestionably
    -0.08
    meni
    -0.07
    τερ
    -0.07
     pasión
    -0.07
    vaard
    -0.07
    Neill
    -0.07
    hely
    -0.07
    POSITIVE LOGITS
    pct
    0.08
     אי�
    0.08
     pct
    0.08
    acement
    0.07
     curls
    0.07
     هن
    0.07
     האפשר
    0.07
    -print
    0.07
    ofar
    0.07
    iranje
    0.07
    Activations Density 0.001%

    No Known Activations