© 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 EvalsExportsinterp-engineNEWAPI 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. 18987
    Prev
    Next
    INDEX
    Explanations

    But

    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
     jedenfalls
    -0.10
     somit
    -0.10
     ذلك
    -0.10
     그러나
    -0.10
     hence
    -0.10
    ardless
    -0.10
     aparentemente
    -0.10
     thus
    -0.09
     generalmente
    -0.09
     결국
    -0.09
    POSITIVE LOGITS
     include
    0.13
     provide
    0.11
     ensure
    0.11
     also
    0.11
     incorporate
    0.11
     want
    0.11
     wants
    0.11
    Also
    0.11
    <|end|>
    0.10
     Also
    0.10
    Activations Density 0.048%

    No Known Activations