© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 48209
    Prev
    Next
    INDEX
    Explanations

    peng

    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
    ’agit
    -0.08
     fordel
    -0.08
    OUTH
    -0.08
     ens
    -0.07
    Dedicated
    -0.07
    ismod
    -0.07
     заслуж
    -0.07
    �
    -0.07
    ouvrez
    -0.07
    otate
    -0.07
    POSITIVE LOGITS
    embangan
    0.22
    iriman
    0.21
    gunaan
    0.20
    awasan
    0.20
    aturan
    0.19
    umpulan
    0.19
    urangan
    0.18
    ajuan
    0.18
    uatan
    0.18
    aruh
    0.18
    Activations Density 0.001%

    No Known Activations