Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 58790
    Prev
    Next
    INDEX
    Explanations

    1

    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
    -author
    -0.09
    Doctor
    -0.08
    _author
    -0.08
     κυβέρνηση
    -0.08
    -good
    -0.08
    (author
    -0.08
    Heroes
    -0.08
    _tables
    -0.08
    Artwork
    -0.08
    ();
    -0.08
    POSITIVE LOGITS
     MT
    0.08
     Vf
    0.07
     Zi
    0.07
    Beschreibung
    0.07
     Shin
    0.07
     TBD
    0.07
     load
    0.07
    MT
    0.07
     Beschreibung
    0.07
    ldi
    0.07
    Activations Density 0.000%

    No Known Activations