© 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. 68067
    Prev
    Next
    INDEX
    Explanations

    ×

    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
     तेज
    -0.08
    %^
    -0.08
    Alphabet
    -0.07
     Lim
    -0.07
     Alphabet
    -0.07
    round
    -0.07
    -tight
    -0.07
     talents
    -0.07
    tight
    -0.07
     alphabet
    -0.07
    POSITIVE LOGITS
     stare
    0.09
    раст
    0.08
    Hx
    0.08
     dif
    0.08
    ')):↵
    0.08
     avr
    0.08
     prat
    0.07
     mam
    0.07
    avou
    0.07
     remboursement
    0.07
    Activations Density 0.001%

    No Known Activations