© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 95175
    Prev
    Next
    INDEX
    Explanations

    lava

    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
     respectfully
    -0.09
     systematically
    -0.09
     brit
    -0.08
     optar
    -0.08
     Wellington
    -0.08
     Columbus
    -0.08
     Vereinig
    -0.08
     glück
    -0.08
    Victoria
    -0.08
     शांत
    -0.07
    POSITIVE LOGITS
     forbidden
    0.08
     subnet
    0.07
    uth
    0.07
    Forbidden
    0.07
     produced
    0.07
     SP
    0.07
     injured
    0.07
    Imm
    0.07
    Impossible
    0.07
     jailed
    0.07
    Activations Density 0.002%

    No Known Activations