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. 30011
    Prev
    Next
    INDEX
    Explanations

    physics and springs

    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
    curse
    -0.08
     volupt
    -0.08
     awe
    -0.08
     Brendan
    -0.08
     ופ
    -0.08
     Oude
    -0.07
     סיפ
    -0.07
    cü
    -0.07
     policing
    -0.07
     cerebral
    -0.07
    POSITIVE LOGITS
     undergoing
    0.11
     subjected
    0.11
     governed
    0.10
     identical
    0.09
    Equation
    0.09
     પાસે
    0.09
     Equation
    0.09
     cuja
    0.08
     semiconductor
    0.08
     vibrating
    0.08
    Activations Density 0.027%

    No Known Activations