© 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. 24820
    Prev
    Next
    INDEX
    Explanations

    of

    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
     이렇게
    -0.08
     Represent
    -0.08
    З
    -0.07
     represented
    -0.07
     해야
    -0.07
    ００
    -0.07
     그렇게
    -0.07
     Alessandro
    -0.07
     genet
    -0.07
    Represent
    -0.07
    POSITIVE LOGITS
     pajamas
    0.09
    	pw
    0.08
    ector
    0.07
     papier
    0.07
     Rye
    0.07
     uptime
    0.07
     beachfront
    0.07
     ټولو
    0.07
    ieważ
    0.07
     نوع
    0.07
    Activations Density 0.000%

    No Known Activations