© 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. 65482
    Prev
    Next
    INDEX
    Explanations

    clar

    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
    zag
    -0.09
     fake
    -0.09
     bajos
    -0.08
     diffus
    -0.08
     Али
    -0.08
     uncomp
    -0.07
    rekt
    -0.07
     TI
    -0.07
     Elimin
    -0.07
     ISS
    -0.07
    POSITIVE LOGITS
     כל
    0.08
     intrigued
    0.07
     neutron
    0.07
     לצ
    0.07
    ے
    0.07
     intrigu
    0.07
    ыс
    0.07
     בש
    0.07
    Roman
    0.07
     intrins
    0.07
    Activations Density 0.006%

    No Known Activations