© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 1254
    Prev
    Next
    INDEX
    Explanations

    mirror

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    161
    -0.08
     masquer
    -0.07
     પાસે
    -0.07
    तान
    -0.07
     mala
    -0.07
     الق
    -0.07
    Oops
    -0.07
     blem
    -0.07
    ريبة
    -0.07
    _tab
    -0.07
    POSITIVE LOGITS
     pu
    0.08
     Merc
    0.08
    ewu
    0.08
     Cougar
    0.07
     mito
    0.07
    ការ�
    0.07
     ciò
    0.07
     controversy
    0.07
     Bog
    0.07
    etchup
    0.07
    Activations Density 0.008%

    No Known Activations