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. 117570
    Prev
    Next
    INDEX
    Explanations

    of

    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
    scaled
    -0.08
     Felt
    -0.08
     typed
    -0.07
     Amph
    -0.07
     ample
    -0.07
     యొక్క
    -0.07
     മുൻ
    -0.07
     cleans
    -0.07
    sono
    -0.07
     ചേ
    -0.07
    POSITIVE LOGITS
    Instead
    0.10
     Instead
    0.09
     вместо
    0.09
     instead
    0.08
     istället
    0.08
     nicotine
    0.08
     ahubwo
    0.07
    Rainbow
    0.07
     बजाय
    0.07
     إقامة
    0.07
    Activations Density 0.013%

    No Known Activations