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. 98270
    Prev
    Next
    INDEX
    Explanations

    ides

    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
    ERS
    -0.11
    ers
    -0.11
    ings
    -0.10
    ertime
    -0.09
    INGS
    -0.09
    wera
    -0.09
    oniem
    -0.08
    ర్స్
    -0.08
    amentos
    -0.08
     arbitrary
    -0.08
    POSITIVE LOGITS
    cence
    0.26
    cent
    0.24
    цент
    0.17
    CENT
    0.16
     cent
    0.16
    _cent
    0.15
    cente
    0.15
    centes
    0.14
    Cent
    0.14
    .cent
    0.14
    Activations Density 0.003%

    No Known Activations