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. 7-RESID-POST-AA
    6. 131010
    Prev
    Next
    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flores
    -0.08
    pered
    -0.08
    мест
    -0.07
     Wes
    -0.07
    ,而
    -0.07
     것을
    -0.07
     encont
    -0.07
    Cher
    -0.07
     Cove
    -0.07
    nonce
    -0.07
    POSITIVE LOGITS
     skil
    0.08
     plane
    0.08
    _STAR
    0.08
    _OPERATION
    0.08
    flight
    0.08
     Gurb
    0.08
     Sharon
    0.07
     MC
    0.07
    _CONTROL
    0.07
     stone
    0.07
    Activations Density 0.360%

    No Known Activations