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. 55851
    Prev
    Next
    INDEX
    Explanations

    Programming methods/functions

    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
     assumption
    -0.09
     variation
    -0.09
    -0.08
     implying
    -0.08
     precautions
    -0.07
     repetitions
    -0.07
    variation
    -0.07
     son's
    -0.07
     quot
    -0.07
     video's
    -0.07
    POSITIVE LOGITS
    :void
    0.09
    <void
    0.09
     outreach
    0.09
     Laufe
    0.08
     nac
    0.08
     Outreach
    0.08
     vo
    0.08
    ՝
    0.08
     Kh
    0.08
     Sir
    0.07
    Activations Density 0.012%

    No Known Activations