© 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. 95407
    Prev
    Next
    INDEX
    Explanations

    Math/physics problems

    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
     hallmark
    -0.09
    👏
    -0.08
    �
    -0.07
    eking
    -0.07
    łości
    -0.07
    melding
    -0.07
     Offering
    -0.07
    woo
    -0.07
    timeline
    -0.07
     Fuck
    -0.07
    POSITIVE LOGITS
     urgently
    0.08
     perjud
    0.08
     blah
    0.08
    〇
    0.08
     _____
    0.07
     موجب
    0.07
     \"
    0.07
     ..."
    0.07
     fi
    0.07
     persegu
    0.07
    Activations Density 0.204%

    No Known Activations