© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 113505
    Prev
    Next
    INDEX
    Explanations

    fit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Indexed
    -0.08
     Seed
    -0.08
     seeded
    -0.08
     pursuits
    -0.08
     Tre
    -0.08
     hexadecimal
    -0.07
     belangen
    -0.07
     grouped
    -0.07
     ನಿರ್ದೇಶ
    -0.07
     separated
    -0.07
    POSITIVE LOGITS
     snug
    0.14
    -fitting
    0.10
    -fit
    0.10
     फिट
    0.10
     বাঁ
    0.09
     Windsor
    0.08
    Fit
    0.08
     맞
    0.08
    �
    0.08
    .fit
    0.08
    Activations Density 0.023%

    No Known Activations