© 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. 26443
    Prev
    Next
    INDEX
    Explanations

    in

    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
    _SMS
    -0.08
     cryptocurrencies
    -0.07
    jad
    -0.07
    972
    -0.07
    łoż
    -0.07
     cryptocurrency
    -0.07
    erdale
    -0.07
     endors
    -0.07
     지원
    -0.07
     decentral
    -0.07
    POSITIVE LOGITS
     airflow
    0.11
     luft
    0.10
    空气
    0.09
     sniff
    0.09
     fluores
    0.09
     aerosol
    0.09
     inhale
    0.09
     lentamente
    0.09
     видно
    0.09
     एयर
    0.08
    Activations Density 0.005%

    No Known Activations