© 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. 23-RESID-POST-AA
    11. 48492
    Prev
    Next
    INDEX
    Explanations

    com

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     №
    -0.07
    ктер
    -0.07
    ктар
    -0.07
     monstr
    -0.07
    Directional
    -0.07
    кті
    -0.07
     pikir
    -0.07
    _PC
    -0.07
    [mem
    -0.07
    نيع
    -0.07
    POSITIVE LOGITS
    ien
    0.16
    ienza
    0.15
    prob
    0.14
    probante
    0.14
    ience
    0.13
    ún
    0.13
    enz
    0.12
    erc
    0.12
    unidad
    0.12
    ienze
    0.11
    Activations Density 0.001%

    No Known Activations