Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 65642
    Prev
    Next
    INDEX
    Explanations

    equations

    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
     spit
    -0.09
     வாய
    -0.09
    /un
    -0.09
    ksiä
    -0.09
    	un
    -0.08
     വിധ
    -0.08
     spits
    -0.08
     dentures
    -0.07
     hygien
    -0.07
     storyline
    -0.07
    POSITIVE LOGITS
    cov
    0.09
     opposing
    0.08
     oppose
    0.08
     Hess
    0.08
    бот
    0.07
     ces
    0.07
     веществ
    0.07
     cov
    0.07
     alerta
    0.07
     compensate
    0.07
    Activations Density 0.003%

    No Known Activations