© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91207
    Prev
    Next
    INDEX
    Explanations

    be

    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
     photovoltaic
    -0.09
     FEM
    -0.09
     Vodafone
    -0.09
     Islamabad
    -0.09
     preschool
    -0.09
     metro
    -0.09
     Femin
    -0.08
    unicip
    -0.08
     menstrual
    -0.08
     feminist
    -0.08
    POSITIVE LOGITS
     aboard
    0.12
     कप्त
    0.10
     азарт
    0.10
     morale
    0.09
    _slave
    0.09
     जह
    0.09
     voyages
    0.09
    赔率
    0.09
     onboard
    0.08
     decisiones
    0.08
    Activations Density 0.008%

    No Known Activations