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. 90217
    Prev
    Next
    INDEX
    Explanations

    styl

    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
     Byron
    -0.09
     прор
    -0.08
     Ames
    -0.08
     Cry
    -0.08
     Bun
    -0.08
     Bever
    -0.07
     Rising
    -0.07
     كس
    -0.07
     totale
    -0.07
     begged
    -0.07
    POSITIVE LOGITS
     dí
    0.08
    _BG
    0.08
    妹
    0.08
    osph
    0.07
    ists
    0.07
    osphere
    0.07
     ausge
    0.07
    phone
    0.07
    phon
    0.07
    ass
    0.07
    Activations Density 0.001%

    No Known Activations