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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98298
    Prev
    Next
    INDEX
    Explanations

    X

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liwe
    -0.09
     weak
    -0.08
     pra
    -0.08
     juillet
    -0.08
    ptive
    -0.08
     abc
    -0.08
     خواب
    -0.08
     июля
    -0.08
     gesam
    -0.08
     הק
    -0.08
    POSITIVE LOGITS
    ion
    0.12
    ION
    0.09
    IÓN
    0.08
    (ph
    0.08
    ŷ
    0.07
    万美元
    0.07
    _phy
    0.07
    0.07
     ventricular
    0.07
    ಿರಿ
    0.07
    Activations Density 0.000%

    No Known Activations