© 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. 24621
    Prev
    Next
    INDEX
    Explanations

    addition and subtraction

    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
    空
    -0.09
    Dick
    -0.08
     Hans
    -0.08
     Homer
    -0.08
     vocalist
    -0.08
     doz
    -0.07
    อด
    -0.07
     Vog
    -0.07
     profunda
    -0.07
     adulthood
    -0.07
    POSITIVE LOGITS
     numerator
    0.12
     denominator
    0.09
    #/
    0.09
    )/(
    0.08
    	source
    0.08
    ాన్ని
    0.08
     divided
    0.08
     denomin
    0.08
     mérite
    0.08
    -related
    0.08
    Activations Density 0.077%

    No Known Activations