© 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. 3-RESID-POST-AA
    11. 12819
    Prev
    Next
    INDEX
    Explanations

    mean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     préd
    -0.08
    Haus
    -0.07
     Pract
    -0.07
     Haus
    -0.07
     haus
    -0.07
     conclus
    -0.07
     cavity
    -0.07
     fus
    -0.06
     stan
    -0.06
     Spe
    -0.06
    POSITIVE LOGITS
     एवं
    0.10
     तथा
    0.10
     glimps
    0.09
     그것
    0.09
     അത്
    0.08
     thereafter
    0.08
     പക്ഷ
    0.08
     તથા
    0.08
     ഞ
    0.08
     എന്നാൽ
    0.08
    Activations Density 0.830%

    No Known Activations