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. 53217
    Prev
    Next
    INDEX
    Explanations

    plus sign

    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
    	N
    -0.08
     Powell
    -0.07
     Pern
    -0.07
     Hath
    -0.07
     indirectly
    -0.07
    -independent
    -0.07
    итесь
    -0.07
     followed
    -0.07
     succession
    -0.07
     சூ
    -0.07
    POSITIVE LOGITS
    adress
    0.09
    Adress
    0.09
     адресу
    0.08
    地址
    0.08
    address
    0.08
     flipping
    0.08
     ieee
    0.08
    _address
    0.08
    ocation
    0.08
    拿
    0.08
    Activations Density 0.002%

    No Known Activations