© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 99128
    Prev
    Next
    INDEX
    Explanations

    cilantro

    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
     Mecklenburg
    -0.08
     Hermann
    -0.08
     �
    -0.08
     мет
    -0.08
     Hert
    -0.07
     Orts
    -0.07
    級
    -0.07
     Somerset
    -0.07
     bd
    -0.07
     schon
    -0.07
    POSITIVE LOGITS
    Dag
    0.10
     Brace
    0.08
    xic
    0.08
    inted
    0.08
    ugated
    0.08
     Rugs
    0.08
     Poison
    0.08
    mla
    0.08
     Soto
    0.08
    Ghost
    0.08
    Activations Density 0.001%

    No Known Activations