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. 76319
    Prev
    Next
    INDEX
    Explanations

    case

    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
    secret
    -0.09
     standpoint
    -0.08
     shake
    -0.08
     agree
    -0.08
    subscribe
    -0.07
     Sammy
    -0.07
    uth
    -0.07
     slachtoffers
    -0.07
    -twitter
    -0.07
     contracted
    -0.07
    POSITIVE LOGITS
    슈
    0.08
     작성
    0.08
    ensatz
    0.08
     regulating
    0.08
    führt
    0.08
     PSC
    0.07
    ড়ে
    0.07
     Paraná
    0.07
    (REG
    0.07
     Turin
    0.07
    Activations Density 0.002%

    No Known Activations