© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 94
    Prev
    Next
    INDEX
    Explanations

    weather

    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
     če
    -0.08
     shed
    -0.08
     (%)
    -0.08
     كه
    -0.08
     दौरान
    -0.08
     कव
    -0.07
     cargo
    -0.07
     sobres
    -0.07
    ापन
    -0.07
     debe
    -0.07
    POSITIVE LOGITS
    "You
    0.08
    .trade
    0.08
    story
    0.08
     analyzes
    0.08
     Victory
    0.08
    “You
    0.07
     predicts
    0.07
     pany
    0.07
    fert
    0.07
    ließ
    0.07
    Activations Density 0.001%

    No Known Activations