© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 47921
    Prev
    Next
    INDEX
    Explanations

    roph

    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
     fiable
    -0.08
    _COMM
    -0.08
     derog
    -0.08
    (comm
    -0.08
    κή
    -0.08
     deixou
    -0.08
     deliciosa
    -0.08
     atraso
    -0.08
     comm
    -0.08
    COMM
    -0.08
    POSITIVE LOGITS
    oves
    0.09
    oh
    0.08
    ied
    0.08
    ilg
    0.08
    ves
    0.08
    ice
    0.07
    ying
    0.07
    skap
    0.07
    rossover
    0.07
     lo
    0.07
    Activations Density 0.000%

    No Known Activations