© 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. 7-RESID-POST-AA
    11. 1510
    Prev
    Next
    INDEX
    Explanations

    Ions and cell biology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dedication
    -0.09
     audiovisual
    -0.09
    Meeting
    -0.09
     originality
    -0.09
     deterior
    -0.08
     ruins
    -0.08
     espí
    -0.08
    投入
    -0.08
     લગ્ન
    -0.08
     deadlines
    -0.08
    POSITIVE LOGITS
     potassium
    0.12
     ions
    0.11
     Voltage
    0.11
    _voltage
    0.09
     adr
    0.09
     चालक
    0.09
     ion
    0.09
     voltage
    0.09
     permeability
    0.09
     Sodium
    0.09
    Activations Density 0.006%

    No Known Activations