© 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. 47940
    Prev
    Next
    INDEX
    Explanations

    Non-English text

    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
     resonates
    -0.08
    וצר
    -0.08
     colo
    -0.08
    וץ
    -0.08
    еж
    -0.07
     están
    -0.07
    IPAddress
    -0.07
     longstanding
    -0.07
    وازې
    -0.07
    ुझ
    -0.07
    POSITIVE LOGITS
    Пар
    0.08
    Chrom
    0.08
    Ei
    0.08
    tek
    0.08
    Land
    0.08
    Thinking
    0.08
    post
    0.08
    Tek
    0.08
    a
    0.08
     paysages
    0.07
    Activations Density 0.000%

    No Known Activations