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. 111959
    Prev
    Next
    INDEX
    Explanations

    space and earth science

    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
    agine
    -0.07
     Assistance
    -0.07
     hita
    -0.07
    肖
    -0.07
     examines
    -0.07
     admin
    -0.07
     Situation
    -0.07
    :outline
    -0.07
     breakdown
    -0.07
     situatie
    -0.07
    POSITIVE LOGITS
     frühen
    0.11
     frü
    0.11
     primordial
    0.10
     während
    0.10
     infant
    0.10
     embryos
    0.10
    统一
    0.10
     первонач
    0.10
     اولیه
    0.10
    Early
    0.10
    Activations Density 0.005%

    No Known Activations