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. 98057
    Prev
    Next
    INDEX
    Explanations

    say the ending -aneous

    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
    RTC
    -0.08
    uttet
    -0.08
     بكل
    -0.08
    Sett
    -0.07
    ിത്സ
    -0.07
     intensely
    -0.07
    Getty
    -0.07
    וסט
    -0.07
    πος
    -0.07
    164
    -0.07
    POSITIVE LOGITS
    aneous
    0.33
    aneously
    0.20
    insic
    0.19
    icating
    0.15
    insics
    0.14
    ane
    0.14
    enuous
    0.14
    icated
    0.14
    restrial
    0.14
    ensic
    0.13
    Activations Density 0.003%

    No Known Activations