© 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. 65408
    Prev
    Next
    INDEX
    Explanations

    's

    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
     ventures
    -0.08
     presencia
    -0.08
     realizados
    -0.08
     persönlich
    -0.08
    రో
    -0.08
     નું
    -0.08
     Elem
    -0.08
     Cena
    -0.07
    Journey
    -0.07
     అనే
    -0.07
    POSITIVE LOGITS
    特色
    0.10
     ethos
    0.08
     treasury
    0.08
    特点
    0.08
    运营
    0.08
    广大
    0.07
     gang
    0.07
    ρα
    0.07
     MVP
    0.07
    出口
    0.07
    Activations Density 0.097%

    No Known Activations