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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 105993
    Prev
    Next
    INDEX
    Explanations

    hand

    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
    gher
    -0.08
    產
    -0.08
    etri
    -0.08
    Interess
    -0.08
     प्रेर
    -0.08
     circulated
    -0.08
     Pilar
    -0.07
    _vert
    -0.07
    itudine
    -0.07
     بالغ
    -0.07
    POSITIVE LOGITS
     melee
    0.08
     accessories
    0.08
     careg
    0.08
     tabla
    0.07
     geprobeerd
    0.07
     MASK
    0.07
     sword
    0.07
     bask
    0.07
     carga
    0.07
     இரண்டு
    0.07
    Activations Density 0.006%

    No Known Activations