© 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. 19-RESID-POST-AA
    11. 102653
    Prev
    Next
    INDEX
    Explanations

    все/всё

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     each
    -0.12
     of
    -0.12
    -of
    -0.09
    ned
    -0.09
    icas
    -0.09
    	of
    -0.09
     some
    -0.08
    ivia
    -0.08
    sof
    -0.08
    uminum
    -0.08
    POSITIVE LOGITS
    -таки
    0.13
    भन्दा
    0.12
    ләй
    0.12
     الملاب
    0.11
    чески
    0.11
    ೕ
    0.11
     più
    0.11
     ваҡыт
    0.11
    ً
    0.10
    ​ដែល
    0.10
    Activations Density 0.005%

    No Known Activations