© 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. 49003
    Prev
    Next
    INDEX
    Explanations

    Names with phonetic transcriptions

    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
     Berdimuhamed
    -0.07
    πόν
    -0.07
    ümay
    -0.07
     ########.
    -0.07
    EVERE
    -0.06
    ’ẽ
    -0.06
     Berdimuhamedow
    -0.06
    çado
    -0.06
    megine
    -0.06
     whakah
    -0.06
    POSITIVE LOGITS
     ல
    0.48
     Л
    0.47
     ಲ
    0.42
    	l
    0.42
     ল
    0.42
    _l
    0.41
    	L
    0.41
    -L
    0.41
    _L
    0.41
    Л
    0.40
    Activations Density 2.867%

    No Known Activations