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. 106055
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Wirtschaft
    -0.07
    aithe
    -0.07
    ители
    -0.07
     Vo
    -0.07
     Medizin
    -0.07
     특징
    -0.07
    clusion
    -0.07
     Membership
    -0.07
     Apr
    -0.07
    องค์
    -0.07
    POSITIVE LOGITS
    remaining
    0.10
     leftover
    0.09
     ಉಳ
    0.09
     restantes
    0.09
    .remaining
    0.09
     restante
    0.09
     reserva
    0.09
     withheld
    0.09
     allocated
    0.09
     remainder
    0.09
    Activations Density 0.012%

    No Known Activations