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. 114015
    Prev
    Next
    INDEX
    Explanations

    calculating angles

    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
     nem
    -0.07
     સરકાર
    -0.07
     du
    -0.07
     incom
    -0.07
     Gorge
    -0.07
     സർക്ക
    -0.07
    vant
    -0.07
     scrum
    -0.07
    _sw
    -0.06
    િસ
    -0.06
    POSITIVE LOGITS
     overflowing
    0.10
     assaults
    0.10
    %m
    0.10
    лол
    0.10
     %=
    0.09
     exces
    0.09
     repetitions
    0.09
    Modulo
    0.09
     modulo
    0.09
     الطويل
    0.09
    Activations Density 0.051%

    No Known Activations