© 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. 5875
    Prev
    Next
    INDEX
    Explanations

    at

    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
    (values
    -0.09
     Cylinder
    -0.09
     Values
    -0.09
    (numbers
    -0.08
     maje
    -0.08
     Werte
    -0.08
     المهمة
    -0.08
     Something
    -0.08
    iation
    -0.08
     Horiz
    -0.08
    POSITIVE LOGITS
     constant
    0.14
    constant
    0.12
     steady
    0.12
     leisurely
    0.12
     konstant
    0.12
     uniform
    0.11
     relentless
    0.11
     reduced
    0.11
     full
    0.11
    _constant
    0.11
    Activations Density 0.045%

    No Known Activations