© 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. 113557
    Prev
    Next
    INDEX
    Explanations

    given

    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
    /oder
    -0.08
    ించాలని
    -0.08
     Weston
    -0.07
    akanaka
    -0.07
     nije
    -0.07
     kein
    -0.07
     unity
    -0.07
     nema
    -0.07
     stakeholder
    -0.07
     Jeanne
    -0.07
    POSITIVE LOGITS
     constraints
    0.11
    Constraints
    0.11
     apparently
    0.10
    constraints
    0.09
     supposedly
    0.09
     presumably
    0.09
     somehow
    0.08
     Constraints
    0.08
     aparentemente
    0.08
     randomly
    0.08
    Activations Density 0.091%

    No Known Activations