© 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. 91431
    Prev
    Next
    INDEX
    Explanations

    media

    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
    ment
    -0.08
    이가
    -0.08
     Antoine
    -0.08
    bp
    -0.08
    แรก
    -0.08
     Jacobs
    -0.08
    antry
    -0.07
    洛
    -0.07
     교수
    -0.07
    spunkt
    -0.07
    POSITIVE LOGITS
     activism
    0.09
     Teams
    0.08
     wellness
    0.08
     fuels
    0.08
     savvy
    0.08
     platforms
    0.08
    ಷ
    0.07
    上的
    0.07
     constituted
    0.07
     Dona
    0.07
    Activations Density 0.015%

    No Known Activations