© 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. 18535
    Prev
    Next
    INDEX
    Explanations

    strength

    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
    AYOUT
    -0.08
     translucent
    -0.08
     alguien
    -0.08
     Mange
    -0.08
    cled
    -0.08
     Concord
    -0.07
     robotic
    -0.07
     muchos
    -0.07
     manages
    -0.07
     ámbitos
    -0.07
    POSITIVE LOGITS
    ening
    0.13
    (training
    0.11
    ened
    0.11
    _training
    0.11
    -training
    0.11
     training
    0.11
    eners
    0.10
    entionally
    0.10
    Training
    0.10
    aining
    0.10
    Activations Density 0.007%

    No Known Activations