Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 74683
    Prev
    Next
    INDEX
    Explanations

    told

    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
    761
    -0.09
     eyewitness
    -0.08
    umato
    -0.07
    702
    -0.07
     ENTRY
    -0.07
     Humph
    -0.07
     Telescope
    -0.07
     Wag
    -0.07
    712
    -0.07
    760
    -0.07
    POSITIVE LOGITS
     laughs
    0.08
    Punch
    0.08
     misma
    0.08
     asleep
    0.08
     pend
    0.07
     spacing
    0.07
    ಗಾರ
    0.07
     justice
    0.07
     corriente
    0.07
     justiça
    0.07
    Activations Density 0.010%

    No Known Activations