© 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. 11-RESID-POST-AA
    11. 129308
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enj
    -0.09
    öll
    -0.07
     bele
    -0.07
    en
    -0.07
    HR
    -0.07
    Bachelor
    -0.07
    ંત્ર
    -0.07
    િક્ષ
    -0.07
     around
    -0.07
     blu
    -0.07
    POSITIVE LOGITS
     ratio
    0.11
     ratios
    0.11
    ratio
    0.10
    Ratio
    0.10
    是多少
    0.10
    _RATIO
    0.10
     Ratio
    0.10
    比分
    0.10
    -wh
    0.09
     celle
    0.09
    Activations Density 0.012%

    No Known Activations