© 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. 30130
    Prev
    Next
    INDEX
    Explanations

    voice

    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
    组
    -0.08
     Parking
    -0.08
     chromium
    -0.07
     mengh
    -0.07
    停车
    -0.07
     geg
    -0.07
    ್ಸ್
    -0.07
     aplik
    -0.07
     Chrom
    -0.07
     经
    -0.07
    POSITIVE LOGITS
     शैली
    0.14
     стиль
    0.13
     tonal
    0.13
     스타일
    0.13
    /style
    0.13
     styles
    0.12
     tones
    0.12
     tone
    0.12
    Tone
    0.12
     stylist
    0.12
    Activations Density 0.035%

    No Known Activations