© 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. 31065
    Prev
    Next
    INDEX
    Explanations

    sh

    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
     smile
    -0.08
     পড়ে
    -0.08
     («
    -0.08
     Guru
    -0.08
     créé
    -0.08
     personnalisé
    -0.08
     automatique
    -0.07
     গাড়
    -0.07
     pozi
    -0.07
     Е
    -0.07
    POSITIVE LOGITS
    菌
    0.08
    ittää
    0.07
    ensão
    0.07
     antibiotic
    0.07
     Nigerian
    0.07
     banheiro
    0.07
     маз
    0.07
    ish
    0.07
    튼
    0.07
     Nigeria
    0.07
    Activations Density 0.000%

    No Known Activations