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. 98038
    Prev
    Next
    INDEX
    Explanations

    fl

    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
    rewrite
    -0.09
    ឹក
    -0.08
    ik
    -0.08
    Cleaning
    -0.08
    Standard
    -0.08
    _FRAGMENT
    -0.08
     Standard
    -0.08
    STD
    -0.07
    ikot
    -0.07
    ဲ
    -0.07
    POSITIVE LOGITS
    zieć
    0.08
    naeth
    0.08
    moil
    0.08
    есс
    0.08
    ੱਚ
    0.07
     innen
    0.07
    ahal
    0.07
     суще
    0.07
     należy
    0.07
    emi
    0.07
    Activations Density 0.000%

    No Known Activations