© 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. 19002
    Prev
    Next
    INDEX
    Explanations

    gap (mathematical)

    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
     heritage
    -0.08
     parsley
    -0.08
     varargin
    -0.08
    Reducer
    -0.08
     karma
    -0.08
     öss
    -0.07
     бүг
    -0.07
     onderdelen
    -0.07
     Ursprung
    -0.07
     ABC
    -0.07
    POSITIVE LOGITS
     gap
    0.16
     gaps
    0.16
    gap
    0.16
    _gap
    0.15
     Gap
    0.15
    Gap
    0.15
     consecutive
    0.15
    -gap
    0.14
     spacing
    0.14
     inequalities
    0.13
    Activations Density 0.032%

    No Known Activations