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. 43422
    Prev
    Next
    INDEX
    Explanations

    a

    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
     Chess
    -0.08
     Conversely
    -0.08
    ೊಂದ
    -0.08
     Calculates
    -0.08
     rir
    -0.08
     Calculation
    -0.08
     Small
    -0.08
     Requirement
    -0.08
    _requirement
    -0.07
     आवश्यकता
    -0.07
    POSITIVE LOGITS
     hopefully
    0.09
    ાહી
    0.08
    Feeling
    0.08
    hopefully
    0.08
    લાક
    0.07
    Luc
    0.07
    Become
    0.07
    rich
    0.07
     genial
    0.07
     become
    0.07
    Activations Density 0.051%

    No Known Activations