© 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. 167
    Prev
    Next
    INDEX
    Explanations

    table

    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
     convictions
    -0.08
     définitivement
    -0.08
     ;↵//
    -0.08
     pedal
    -0.08
    confirmed
    -0.08
     definitivamente
    -0.08
    DAC
    -0.08
     entirety
    -0.08
    barung
    -0.07
     있기
    -0.07
    POSITIVE LOGITS
     קצר
    0.09
     opposed
    0.08
     adhering
    0.08
     ISBN
    0.08
    �
    0.07
     giving
    0.07
     קטן
    0.07
     SWOT
    0.07
    .Port
    0.07
     اشاره
    0.07
    Activations Density 0.007%

    No Known Activations