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. 90943
    Prev
    Next
    INDEX
    Explanations

    Vestibular system

    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
    �
    -0.08
    (c
    -0.07
    (enable
    -0.07
     એ
    -0.07
     interpolation
    -0.07
    Fit
    -0.07
    At
    -0.07
    GOOD
    -0.07
    istas
    -0.07
    atur
    -0.07
    POSITIVE LOGITS
     Lindsay
    0.09
     Lop
    0.09
     hippoc
    0.08
     कु
    0.08
     wię
    0.08
     Euch
    0.08
     emotionally
    0.08
     Fisheries
    0.08
     Erinner
    0.08
     joe
    0.08
    Activations Density 0.001%

    No Known Activations