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. 61105
    Prev
    Next
    INDEX
    Explanations

    Spinoza

    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
     Tube
    -0.08
     Needle
    -0.07
     Wy
    -0.07
     informeren
    -0.07
     souhait
    -0.07
     pièces
    -0.07
     πληροφο
    -0.07
    _interp
    -0.07
    lij
    -0.07
     healthcare
    -0.07
    POSITIVE LOGITS
     planted
    0.08
    голь
    0.08
    	H
    0.08
     consequ
    0.08
    ګې
    0.08
     calming
    0.08
     (:
    0.08
    ડી
    0.07
    город
    0.07
     maior
    0.07
    Activations Density 0.000%

    No Known Activations