© 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. 97336
    Prev
    Next
    INDEX
    Explanations

    decimal point

    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
    Discrete
    -0.08
    Numeric
    -0.08
     numerical
    -0.08
    Numer
    -0.08
    numer
    -0.08
     Numerical
    -0.08
     临
    -0.08
     discrete
    -0.07
     Numeric
    -0.07
    numeric
    -0.07
    POSITIVE LOGITS
     зап
    0.14
     deset
    0.14
     деся
    0.13
     пла
    0.13
     coma
    0.12
     Dec
    0.11
     Зап
    0.11
     Fl
    0.11
     플
    0.11
     फ्ल
    0.11
    Activations Density 0.005%

    No Known Activations