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. 102943
    Prev
    Next
    INDEX
    Explanations

    于

    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
     shirts
    -0.08
    �
    -0.08
     psychiat
    -0.08
    pä
    -0.07
     stockholm
    -0.07
    ार्थ
    -0.07
     bond
    -0.07
    _done
    -0.07
     Toronto
    -0.07
     electroph
    -0.07
    POSITIVE LOGITS
    0.09
    _Server
    0.09
    .Serialized
    0.09
    Yu
    0.09
     HDMI
    0.09
     tecnologias
    0.09
     Yu
    0.08
    .module
    0.08
     VMware
    0.08
     tecnologia
    0.08
    Activations Density 0.011%

    No Known Activations