© 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. 23-RESID-POST-AA
    11. 50971
    Prev
    Next
    INDEX
    Explanations

    il

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .true
    -0.09
    beautiful
    -0.09
    _true
    -0.09
    _UNKNOWN
    -0.08
    bers
    -0.08
    awesome
    -0.08
     وڏي
    -0.08
    _NE
    -0.08
    very
    -0.08
    omi
    -0.08
    POSITIVE LOGITS
     faud
    0.16
     convient
    0.15
     plaît
    0.13
     convi
    0.12
     faut
    0.11
     fallait
    0.11
     leur
    0.11
     manque
    0.11
     lui
    0.10
     faudrait
    0.10
    Activations Density 0.006%

    No Known Activations