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. 103125
    Prev
    Next
    INDEX
    Explanations

    Coral

    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
    adto
    -0.09
     Rund
    -0.09
    فاف
    -0.08
     interv
    -0.08
    lager
    -0.08
    Owned
    -0.08
     ځ
    -0.08
    Database
    -0.08
    Hide
    -0.08
    باد
    -0.08
    POSITIVE LOGITS
     bestehen
    0.08
     handheld
    0.08
     inspectors
    0.08
     trainers
    0.07
     Elementor
    0.07
     Trainers
    0.07
    elligence
    0.07
     museums
    0.07
     detectors
    0.07
     urges
    0.07
    Activations Density 0.001%

    No Known Activations