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. 12690
    Prev
    Next
    INDEX
    Explanations

    3

    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
    Real
    -0.08
    Note
    -0.07
     tremendously
    -0.07
    _note
    -0.07
     therapeutic
    -0.07
    inda
    -0.07
    real
    -0.07
    ankha
    -0.07
    יי
    -0.07
    Bindable
    -0.07
    POSITIVE LOGITS
    ்க்க
    0.08
            
    0.08
     thirds
    0.08
     Occup
    0.08
    เภท
    0.08
     ■
    0.08
     gcd
    0.08
     Provid
    0.07
     தேசிய
    0.07
    faz
    0.07
    Activations Density 0.021%

    No Known Activations