© 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. 48202
    Prev
    Next
    INDEX
    Explanations

    we

    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
     requiring
    -0.12
     требует
    -0.11
     requires
    -0.11
    requires
    -0.11
    Requires
    -0.11
     requiere
    -0.11
     Requires
    -0.11
     nécessite
    -0.11
     requieren
    -0.11
     Require
    -0.11
    POSITIVE LOGITS
     cannot
    0.16
     shouldn't
    0.15
     can't
    0.15
     wouldn't
    0.15
    不能
    0.14
    cannot
    0.14
    Cannot
    0.14
     won't
    0.14
     shouldn
    0.13
    Avoid
    0.13
    Activations Density 0.066%

    No Known Activations