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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 47997
    Prev
    Next
    INDEX
    Explanations

    Solar

    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
     tela
    -0.09
     bacterial
    -0.08
    Tela
    -0.08
     panic
    -0.08
     unidades
    -0.08
     painel
    -0.08
     repent
    -0.08
     charged
    -0.08
     infek
    -0.08
    Pads
    -0.07
    POSITIVE LOGITS
     parks
    0.10
     ફોટ
    0.10
    parks
    0.09
     Phot
    0.09
     Arlington
    0.08
     fot
    0.08
     फोटो
    0.08
     Parks
    0.08
     markets
    0.08
    rooms
    0.08
    Activations Density 0.002%

    No Known Activations