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. 98430
    Prev
    Next
    INDEX
    Explanations

    unrecognized token

    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
    amman
    -0.07
     felt
    -0.07
    īd
    -0.07
    ngr
    -0.07
    ensen
    -0.07
     fondos
    -0.07
    때
    -0.07
    GAN
    -0.07
    (words
    -0.07
     �
    -0.07
    POSITIVE LOGITS
     Strand
    0.07
    GES
    0.07
     راه
    0.07
    ொள்ள
    0.07
    луж
    0.07
    ్ష
    0.07
    Projection
    0.07
    ็ต
    0.07
     projection
    0.07
    rsat
    0.07
    Activations Density 0.000%

    No Known Activations