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. 45037
    Prev
    Next
    INDEX
    Explanations

    sphere packing

    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
     обс
    -0.08
     film
    -0.08
     poss
    -0.08
    lectic
    -0.07
    obili
    -0.07
     isu
    -0.07
    Pris
    -0.07
    Cord
    -0.07
     batch
    -0.07
    _batch
    -0.07
    POSITIVE LOGITS
     theorem
    0.09
     radically
    0.08
     encrypt
    0.08
     entsprechend
    0.08
    ','#
    0.07
    assert
    0.07
     Expanded
    0.07
     expanded
    0.07
    encrypt
    0.07
    írus
    0.07
    Activations Density 0.005%

    No Known Activations