© 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. 23-RESID-POST-AA
    11. 96941
    Prev
    Next
    INDEX
    Explanations

    п

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     KL
    -0.08
    ERATOR
    -0.08
    कर्त
    -0.08
    ARI
    -0.08
    OUS
    -0.08
    NING
    -0.08
    GP
    -0.08
    ATEGORIES
    -0.08
    ੰਡ
    -0.08
    TE
    -0.08
    POSITIVE LOGITS
    лей
    0.10
    ойн
    0.09
     મુજબ
    0.08
    ле
    0.08
    covery
    0.08
     נ
    0.08
     apresenta
    0.08
    ુ
    0.07
    ्ले
    0.07
    ад
    0.07
    Activations Density 0.001%

    No Known Activations