© 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. 47732
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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
     Civic
    -0.07
    =k
    -0.07
    433
    -0.07
     consisting
    -0.07
    	g
    -0.07
    belasting
    -0.07
     retras
    -0.07
    -g
    -0.07
    inned
    -0.06
     Innoc
    -0.06
    POSITIVE LOGITS
    ורג
    0.08
    زع
    0.08
     شعار
    0.08
    ڑی
    0.08
     پرا
    0.08
     jaune
    0.08
     जाह
    0.07
    _TC
    0.07
     dabei
    0.07
    žje
    0.07
    Activations Density 0.000%

    No Known Activations