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. 59172
    Prev
    Next
    INDEX
    Explanations

    Period

    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
    Nib
    -0.08
    Reducers
    -0.08
    Reducer
    -0.08
    igrate
    -0.08
    期间
    -0.08
    Policy
    -0.08
    ible
    -0.07
    utto
    -0.07
    Threshold
    -0.07
    rement
    -0.07
    POSITIVE LOGITS
     ambiance
    0.10
     ambience
    0.09
     watercolor
    0.09
     समुद
    0.08
     vibe
    0.08
     painting
    0.08
     атмос
    0.08
     शाम
    0.08
     выполн
    0.08
     будто
    0.08
    Activations Density 0.012%

    No Known Activations