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. 75018
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     collisions
    -0.08
     parasites
    -0.08
     Allies
    -0.08
     symbols
    -0.07
     czym
    -0.07
    .random
    -0.07
    lamak
    -0.07
    เท
    -0.07
    .mnu
    -0.07
     crews
    -0.07
    POSITIVE LOGITS
    Understanding
    0.09
     Humb
    0.09
    Compound
    0.08
     Pontiac
    0.08
     tucked
    0.08
    Ei
    0.08
     autistic
    0.08
     hübs
    0.08
     gert
    0.08
    Nationality
    0.08
    Activations Density 0.006%

    No Known Activations