© 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. 11-RESID-POST-AA
    6. 8088
    Prev
    Next
    INDEX
    Explanations

    algorithmic selection

    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
    arnings
    -0.08
     tur
    -0.08
     effectiveness
    -0.07
    (blank
    -0.07
    .MEDIA
    -0.07
    θυν
    -0.07
     benim
    -0.07
    /html
    -0.07
     Mario
    -0.07
     *>
    -0.07
    POSITIVE LOGITS
     ranger
    0.09
     kth
    0.09
    ron
    0.08
     earm
    0.08
    bower
    0.08
     पत्रकार
    0.08
     отб
    0.08
     اث
    0.08
     Heap
    0.08
    rina
    0.08
    Activations Density 0.002%

    No Known Activations