© 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. 91337
    Prev
    Next
    INDEX
    Explanations

    Ski

    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
    October
    -0.10
     SPELL
    -0.08
    .mobile
    -0.08
     acidic
    -0.08
    Japanese
    -0.08
     prawa
    -0.08
     Chalk
    -0.07
    中国特色
    -0.07
    -uppercase
    -0.07
    Hij
    -0.07
    POSITIVE LOGITS
     więc
    0.09
     programmable
    0.08
     키
    0.08
     оборуд
    0.08
     Fre
    0.07
     확대
    0.07
     bpm
    0.07
     مكت
    0.07
     itil
    0.07
     velocidades
    0.07
    Activations Density 0.010%

    No Known Activations