© 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. 97369
    Prev
    Next
    INDEX
    Explanations

    Acceptable

    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
     yoğun
    -0.09
     intensely
    -0.09
     extreem
    -0.09
     شدت
    -0.09
     low
    -0.09
     extreme
    -0.08
     insanely
    -0.08
     altamente
    -0.08
     ideal
    -0.08
     maximize
    -0.08
    POSITIVE LOGITS
     acceptable
    0.21
     adequate
    0.21
     decent
    0.21
     competent
    0.20
     satisfactory
    0.19
     okay
    0.18
     respectable
    0.18
     alright
    0.18
     solid
    0.17
     competente
    0.17
    Activations Density 0.040%

    No Known Activations