© 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. 96870
    Prev
    Next
    INDEX
    Explanations

    Superman-related characters

    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
     मुख
    -0.09
     exigir
    -0.08
     númer
    -0.08
    itti
    -0.08
    -gh
    -0.07
     Dracula
    -0.07
     sombra
    -0.07
     burglar
    -0.07
     الليل
    -0.07
    'homme
    -0.07
    POSITIVE LOGITS
     Lois
    0.09
     Lena
    0.09
    元
    0.09
     Lex
    0.08
     Chili
    0.08
     CCS
    0.08
     Monitor
    0.08
     Small
    0.08
     bottled
    0.08
     Lionel
    0.08
    Activations Density 0.005%

    No Known Activations