Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 97121
    Prev
    Next
    INDEX
    Explanations

    Xerox

    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
    ichtigen
    -0.08
    саж
    -0.08
    ώς
    -0.08
    াস্ত
    -0.08
    써
    -0.08
    יכער
    -0.08
     қою
    -0.07
     хорош
    -0.07
    ינ
    -0.07
    込み
    -0.07
    POSITIVE LOGITS
    /X
    0.14
    treme
    0.12
    =X
    0.11
    ,X
    0.11
    avier
    0.11
    :X
    0.10
     Jinping
    0.10
    .X
    0.10
    ħra
    0.10
    qqaat
    0.10
    Activations Density 0.043%

    No Known Activations