© 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 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. 50236
    Prev
    Next
    INDEX
    Explanations

    say "icularly"

    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
    േഷൻ
    -0.10
    ేషన్
    -0.10
    ОВ
    -0.10
    ATION
    -0.09
    ATIONS
    -0.09
    ാസ്
    -0.09
    న్స్
    -0.09
    േഷന്
    -0.09
    ാഫ
    -0.09
     mab
    -0.09
    POSITIVE LOGITS
    icularly
    0.21
    iculares
    0.15
    icul
    0.15
    icuous
    0.13
    uc
    0.13
    iculas
    0.13
    icula
    0.12
    ic
    0.12
    cular
    0.11
    icu
    0.11
    Activations Density 0.000%

    No Known Activations