© 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. 30157
    Prev
    Next
    INDEX
    Explanations

    brown

    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
     tät
    -0.08
    üren
    -0.08
    -short
    -0.08
     нанес
    -0.08
     bilm
    -0.07
     vormt
    -0.07
     Tät
    -0.07
     Creating
    -0.07
     Ligne
    -0.07
     precisely
    -0.07
    POSITIVE LOGITS
     insan
    0.08
    旅
    0.07
    Recovered
    0.07
     kef
    0.07
     kana
    0.07
     quinoa
    0.07
    $/
    0.07
    ziehen
    0.07
    /be
    0.07
     pineapple
    0.07
    Activations Density 0.001%

    No Known Activations