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. 98186
    Prev
    Next
    INDEX
    Explanations

    w

    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
     indiqué
    -0.10
    ాస
    -0.09
     Nied
    -0.08
    ್ಡ
    -0.08
    ල්ල
    -0.08
     кең
    -0.08
    RGCTX
    -0.08
    ్�
    -0.07
     نس
    -0.07
    ్డ
    -0.07
    POSITIVE LOGITS
    arks
    0.09
    ark
    0.09
    akwe
    0.09
    ji
    0.08
    ang
    0.08
    aker
    0.08
    ából
    0.08
    oue
    0.08
    allback
    0.08
    .Var
    0.08
    Activations Density 0.000%

    No Known Activations