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. 112984
    Prev
    Next
    INDEX
    Explanations

    previous

    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
     clinicians
    -0.08
    framt
    -0.08
     HM
    -0.07
     casualties
    -0.07
     brochures
    -0.07
     signatures
    -0.07
    _MULTI
    -0.07
    etter
    -0.07
     candidates
    -0.07
     Willow
    -0.07
    POSITIVE LOGITS
     предыдущ
    0.12
     précédente
    0.12
    .previous
    0.11
     السابقة
    0.11
     पिछ
    0.11
     popr
    0.11
     précédent
    0.10
     Previous
    0.10
     पिछले
    0.10
    Previous
    0.10
    Activations Density 0.014%

    No Known Activations