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. 76206
    Prev
    Next
    INDEX
    Explanations

    wait no

    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
     మాట
    -0.08
     करू
    -0.08
     amm
    -0.07
     konnte
    -0.07
     тех
    -0.07
     bo
    -0.07
     dishes
    -0.07
    pai
    -0.07
    ór
    -0.07
     könnt
    -0.07
    POSITIVE LOGITS
     conden
    0.08
     Dup
    0.08
     incest
    0.08
    ثل
    0.07
    rd
    0.07
    082
    0.07
    opro
    0.07
    standen
    0.07
     gant
    0.07
    唐
    0.07
    Activations Density 0.025%

    No Known Activations