© 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. 24606
    Prev
    Next
    INDEX
    Explanations

    head movements/positions

    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
     viscosity
    -0.08
    izza
    -0.08
     Texans
    -0.07
    nder
    -0.07
    zens
    -0.07
    .lex
    -0.07
     Luxembourg
    -0.07
     Loz
    -0.07
    odes
    -0.07
     ......
    -0.07
    POSITIVE LOGITS
     responsabilités
    0.09
    urgeon
    0.08
     nwanyị
    0.08
     curios
    0.08
     fari
    0.08
    หัว
    0.08
    αγ
    0.08
    yr
    0.08
     അഭിപ്രായ
    0.08
    collapse
    0.08
    Activations Density 0.002%

    No Known Activations