© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 108717
    Prev
    Next
    INDEX
    Explanations

    more

    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
     exercised
    -0.07
     peeled
    -0.07
     UE
    -0.07
     responses
    -0.07
    atk
    -0.07
    吕
    -0.07
     kier
    -0.07
    of
    -0.07
    angi
    -0.06
     instr
    -0.06
    POSITIVE LOGITS
     ஆகிய
    0.11
     Stuff
    0.09
     далее
    0.09
    등
    0.09
    ,以及
    0.09
    etera
    0.09
     dependiendo
    0.09
     ذلك
    0.09
     toda
    0.09
     എന്നിവ
    0.08
    Activations Density 0.025%

    No Known Activations