Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 48257
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    cro
    -0.09
     hopp
    -0.08
    Cro
    -0.08
    HB
    -0.07
    kip
    -0.07
     ക്ര
    -0.07
    ertown
    -0.07
     march
    -0.07
     effective
    -0.07
     transactions
    -0.07
    POSITIVE LOGITS
     शाम
    0.10
     Plat
    0.10
    Ladies
    0.08
     vehe
    0.08
     mempert
    0.08
     Tribunal
    0.08
    嘿
    0.08
     Lider
    0.08
     TT
    0.08
     Titans
    0.08
    Activations Density 0.089%

    No Known Activations