Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43505
    Prev
    Next
    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ngā
    -0.09
    والو
    -0.09
    μφωνα
    -0.09
    შირ
    -0.09
    ​ច
    -0.08
     pera
    -0.08
     আহ
    -0.08
    ubliceerd
    -0.08
    խան
    -0.08
     চেয়ারম্যান
    -0.08
    POSITIVE LOGITS
    ipto
    0.10
     world's
    0.07
    REAT
    0.07
     area's
    0.07
    unned
    0.07
    .trace
    0.07
    IALOG
    0.07
     NAT
    0.07
     IMO
    0.07
     organization
    0.07
    Activations Density 0.000%

    No Known Activations