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. 55535
    Prev
    Next
    INDEX
    Explanations

    3

    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
    inity
    -0.08
     katt
    -0.08
     biodegradable
    -0.08
     Morph
    -0.07
     spaz
    -0.07
    Morph
    -0.07
     thromb
    -0.07
     fost
    -0.07
     persen
    -0.07
     العدد
    -0.07
    POSITIVE LOGITS
     remed
    0.08
     Hp
    0.08
     wors
    0.08
    (H
    0.07
     informal
    0.07
     exacerb
    0.07
    (G
    0.07
    Removing
    0.07
     ഏത
    0.07
     embellished
    0.07
    Activations Density 0.001%

    No Known Activations