© 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. 23-RESID-POST-AA
    11. 96968
    Prev
    Next
    INDEX
    Explanations

    thermal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agena
    -0.08
     Ons
    -0.08
    قام
    -0.08
    બ્દ
    -0.08
    াষ
    -0.08
    ahrenheit
    -0.08
    ondissement
    -0.08
    ians
    -0.08
    દ્ધ
    -0.08
    iler
    -0.08
    POSITIVE LOGITS
     bridging
    0.12
     bridges
    0.09
     mass
    0.09
     imagery
    0.09
     imaging
    0.09
    mass
    0.09
     brid
    0.09
     комфорт
    0.08
    izeit
    0.08
     Brid
    0.08
    Activations Density 0.002%

    No Known Activations