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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 51116
    Prev
    Next
    INDEX
    Explanations

    roman numeral II

    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
     third
    -0.21
    Third
    -0.20
     Third
    -0.20
     fourth
    -0.19
     Fourth
    -0.19
    Fourth
    -0.19
    third
    -0.19
    第三
    -0.19
     треть
    -0.18
    第四
    -0.18
    POSITIVE LOGITS
     ii
    0.23
    ii
    0.22
    [ii
    0.20
    (ii
    0.20
     II
    0.19
    II
    0.18
    ②
    0.15
    -II
    0.14
     yy
    0.13
    二
    0.13
    Activations Density 0.037%

    No Known Activations