© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 96799
    Prev
    Next
    INDEX
    Explanations

    Mindfulness and meditation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tie
    -0.09
     tie
    -0.08
     jointly
    -0.08
    总代
    -0.07
    Tie
    -0.07
    [{
    -0.07
    .Re
    -0.07
    ecz
    -0.07
    ūsų
    -0.07
    čev
    -0.07
    POSITIVE LOGITS
     rainy
    0.09
     વર્�
    0.08
     rusty
    0.08
     તાલ
    0.08
     obdob
    0.08
    _url
    0.08
    dda
    0.08
     તર
    0.08
    ойдет
    0.08
     swo
    0.07
    Activations Density 0.000%

    No Known Activations