© 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. 103017
    Prev
    Next
    INDEX
    Explanations

    doubts and surprises

    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
     \<
    -0.09
     atawa
    -0.09
     Verhalten
    -0.09
     onderdelen
    -0.09
    \<
    -0.08
     oder
    -0.08
    <Float
    -0.08
     اقدامات
    -0.08
     aanleg
    -0.08
     drivetrain
    -0.08
    POSITIVE LOGITS
     perhaps
    0.11
     here
    0.10
    this
    0.10
     this
    0.10
     to
    0.09
     सांग
    0.09
     here's
    0.09
    -
    0.09
     aqui
    0.09
     azonban
    0.09
    Activations Density 0.517%

    No Known Activations