© 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. 44789
    Prev
    Next
    INDEX
    Explanations

    Vehicle suspension

    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
    Alphabet
    -0.09
     alfabet
    -0.09
     multilingual
    -0.09
     alphabetical
    -0.09
    Lex
    -0.08
    Dialect
    -0.08
     lex
    -0.08
     directive
    -0.08
    Plural
    -0.08
     multipart
    -0.08
    POSITIVE LOGITS
     damping
    0.11
     smoothing
    0.11
     cushioning
    0.10
     мышцы
    0.09
     springs
    0.09
     stiffness
    0.09
     spring
    0.09
     земли
    0.08
     damp
    0.08
     stiff
    0.08
    Activations Density 0.020%

    No Known Activations