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. 106060
    Prev
    Next
    INDEX
    Explanations

    of

    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
     assaulted
    -0.08
     সন্ধ
    -0.08
     �
    -0.08
     Judah
    -0.08
     Jeanne
    -0.07
    Fa
    -0.07
     SUP
    -0.07
     mature
    -0.07
    Sou
    -0.07
     amended
    -0.07
    POSITIVE LOGITS
     whether
    0.09
     perfectly
    0.08
    その他
    0.07
     jumlah
    0.07
    -DD
    0.07
     порядок
    0.07
     мест
    0.07
     worries
    0.07
     Herkunft
    0.07
     налич
    0.07
    Activations Density 0.010%

    No Known Activations