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. 11616
    Prev
    Next
    INDEX
    Explanations

    -text

    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
    hada
    -0.09
     hobby
    -0.08
    śród
    -0.08
     deemed
    -0.08
    .await
    -0.07
    -grade
    -0.07
     Kag
    -0.07
    Dragon
    -0.07
     تدري
    -0.07
    福
    -0.07
    POSITIVE LOGITS
     citations
    0.10
     citation
    0.08
    ตอน
    0.08
     republic
    0.08
     cov
    0.08
    амі
    0.08
     Ally
    0.08
    _cov
    0.08
     cites
    0.07
     substitutes
    0.07
    Activations Density 0.001%

    No Known Activations