© 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. 21978
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     possibly
    -0.10
     specific
    -0.09
     other
    -0.08
     types
    -0.08
     scenarios
    -0.08
     perhaps
    -0.08
     potentially
    -0.08
     methods
    -0.08
     different
    -0.08
     scenario
    -0.08
    POSITIVE LOGITS
    (\
    0.17
    ((
    0.16
    (/\
    0.12
    ("\
    0.12
    ([
    0.12
    (`
    0.12
    (()
    0.11
    ('\
    0.11
    (((
    0.11
    .\
    0.11
    Activations Density 0.017%

    No Known Activations