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. 12658
    Prev
    Next
    INDEX
    Explanations

    seed

    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
    Ingrese
    -0.08
     monto
    -0.08
    itaan
    -0.08
    VAS
    -0.08
    Monto
    -0.08
     Caesars
    -0.08
     Bretagne
    -0.08
     redux
    -0.07
     faill
    -0.07
     ब्य
    -0.07
    POSITIVE LOGITS
    芽
    0.10
     seeds
    0.10
     graines
    0.09
    sound
    0.09
    子
    0.09
     sound
    0.09
     capsules
    0.09
     رشد
    0.09
    (sound
    0.09
     sementes
    0.08
    Activations Density 0.021%

    No Known Activations