© 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. 128
    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
    etheus
    -0.08
     schemes
    -0.08
    TURE
    -0.08
    sche
    -0.08
     schematic
    -0.08
    zilla
    -0.08
    Disconnect
    -0.08
     Plans
    -0.08
    olated
    -0.08
    verters
    -0.07
    POSITIVE LOGITS
     opportunity
    0.12
     Gelegenheit
    0.11
    机会
    0.11
     oportunidade
    0.11
     privil
    0.10
     मौका
    0.10
     privilege
    0.10
     kesempatan
    0.10
     అవకాశం
    0.10
     Opportunity
    0.09
    Activations Density 0.019%

    No Known Activations