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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 56133
    Prev
    Next
    INDEX
    Explanations

    br

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     તમામ
    -0.08
     epis
    -0.08
     envelop
    -0.08
     té
    -0.08
     Nobel
    -0.08
     Sime
    -0.08
     ಪ್ರಸ
    -0.08
     vseh
    -0.07
     அனைத்து
    -0.07
     чар
    -0.07
    POSITIVE LOGITS
    str
    0.08
    carry
    0.08
    hasil
    0.08
     分
    0.07
     പോല
    0.07
    ണ്ട
    0.07
     torn
    0.07
     എന്നീ
    0.07
     എന്നിവ
    0.07
    gc
    0.07
    Activations Density 0.001%

    No Known Activations