© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 49939
    Prev
    Next
    INDEX
    Explanations

    Great

    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
    060
    -0.08
    anova
    -0.08
    -electric
    -0.08
     egingo
    -0.08
    Animating
    -0.07
    აძ
    -0.07
     forget
    -0.07
    abwa
    -0.07
    აძის
    -0.07
    poň
    -0.07
    POSITIVE LOGITS
     OPC
    0.09
    сти
    0.08
     Gatsby
    0.08
    yse
    0.08
     Opcode
    0.08
     G
    0.08
     Alone
    0.08
     Het
    0.07
     Bericht
    0.07
     Vic
    0.07
    Activations Density 0.003%

    No Known Activations