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. 15-RESID-POST-AA
    6. 175
    Prev
    Next
    INDEX
    Explanations

    words meaning "required"

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    infos
    -0.08
     Bears
    -0.07
    (method
    -0.07
    ासन
    -0.07
    ZF
    -0.07
    _ori
    -0.07
    ило
    -0.07
     स्वागत
    -0.07
    ((((
    -0.07
    ables
    -0.07
    POSITIVE LOGITS
    utuhkan
    0.09
     benodigde
    0.09
     nécess
    0.08
     требуется
    0.08
     Kerk
    0.08
     nodig
    0.08
     چاہیے
    0.08
     понадобится
    0.08
     tarvit
    0.08
     procedimento
    0.08
    Activations Density 0.000%

    No Known Activations