© 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. 19-RESID-POST-AA
    11. 102984
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    （金
    -0.09
    （日
    -0.09
    （三
    -0.09
     ('$
    -0.08
    （二
    -0.08
    三个
    -0.08
     (...
    -0.08
     ({↵
    -0.08
    uhkan
    -0.08
     ("\
    -0.07
    POSITIVE LOGITS
     -
    0.14
     =
    0.11
     aka
    0.11
    =
    0.11
    ՝
    0.10
    简称
    0.10
    ＝
    0.10
     -=
    0.10
     ML
    0.10
     AKA
    0.10
    Activations Density 0.045%

    No Known Activations