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. 130934
    Prev
    Next
    INDEX
    Explanations

    N

    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
    strate
    -0.08
     ప్రమ
    -0.08
     españolas
    -0.08
    pay
    -0.08
    pulse
    -0.08
    quisa
    -0.08
    cha
    -0.07
    .swt
    -0.07
    ’équ
    -0.07
     portuguesa
    -0.07
    POSITIVE LOGITS
    oodles
    0.17
    oodle
    0.15
    ૂડ
    0.12
    ూడ
    0.10
    ू
    0.10
    ודל
    0.10
    ೂ
    0.10
    ori
    0.10
    OOD
    0.10
    Oo
    0.09
    Activations Density 0.000%

    No Known Activations