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. 104306
    Prev
    Next
    INDEX
    Explanations

    parallel lines

    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
    Corner
    -0.08
    tv
    -0.08
    corner
    -0.08
    !:
    -0.08
    兼职
    -0.07
     turbulence
    -0.07
    Payments
    -0.07
    Part
    -0.07
     ഉ
    -0.07
     corner
    -0.07
    POSITIVE LOGITS
     Pase
    0.08
    ayar
    0.08
     développement
    0.08
     promedio
    0.08
    вая
    0.07
     Многие
    0.07
     corazón
    0.07
     cartes
    0.07
    альный
    0.07
     lunar
    0.07
    Activations Density 0.088%

    No Known Activations