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. 61070
    Prev
    Next
    INDEX
    Explanations

    at

    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
     culin
    -0.08
    Fil
    -0.08
     bereid
    -0.08
    Believe
    -0.07
    Belg
    -0.07
    ുമായ
    -0.07
    Fila
    -0.07
    _"
    -0.07
     sprink
    -0.07
     faudra
    -0.07
    POSITIVE LOGITS
     Gull
    0.08
    bly
    0.08
    owler
    0.08
     Poison
    0.08
     palp
    0.07
     glance
    0.07
    附近
    0.07
    灰
    0.07
     Lau
    0.07
     bx
    0.07
    Activations Density 0.020%

    No Known Activations