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. 98373
    Prev
    Next
    INDEX
    Explanations

    Rev

    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
    arsuaq
    -0.09
    heets
    -0.09
    ARRANT
    -0.08
    arneq
    -0.08
     råd
    -0.07
    ערן
    -0.07
    hern
    -0.07
     weer
    -0.07
    רות
    -0.07
    isge
    -0.07
    POSITIVE LOGITS
    ocable
    0.17
    êtement
    0.16
    iving
    0.16
    ocation
    0.16
    ivals
    0.16
    oked
    0.16
    italize
    0.15
    okable
    0.15
    amped
    0.15
    ocations
    0.15
    Activations Density 0.008%

    No Known Activations