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. 55634
    Prev
    Next
    INDEX
    Explanations

    comparable

    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
    áil
    -0.08
    Analytics
    -0.08
     chéad
    -0.08
    icals
    -0.08
    ailer
    -0.08
    _PASSWORD
    -0.08
     Analytics
    -0.08
     analytics
    -0.08
    place
    -0.08
     bienvenida
    -0.07
    POSITIVE LOGITS
     incomparable
    0.14
     neither
    0.11
    Neither
    0.10
     никак
    0.09
    .undefined
    0.09
     direction
    0.09
     കമ്മ
    0.09
     ambigu
    0.09
     Neither
    0.09
    Direction
    0.08
    Activations Density 0.014%

    No Known Activations